Merge remote-tracking branch 'upstream/master' into 30966-str-validate

Author: TomAugspurger

pandas/__init__.py

@@ -35,8 +35,7 @@
     raise ImportError(
         f"C extension: {module} not built. If you want to import "
         "pandas from the source directory, you may need to run "
-        "'python setup.py build_ext --inplace --force' to build "
-        "the C extensions first."
+        "'python setup.py build_ext --inplace --force' to build the C extensions first."
     )
 
 from pandas._config import (
@@ -198,8 +197,7 @@ def __getattr__(name):
 
             warnings.warn(
                 "The Panel class is removed from pandas. Accessing it "
-                "from the top-level namespace will also be removed in "
-                "the next version",
+                "from the top-level namespace will also be removed in the next version",
                 FutureWarning,
                 stacklevel=2,
             )
@@ -238,8 +236,7 @@ class Panel:
         elif name in {"SparseSeries", "SparseDataFrame"}:
             warnings.warn(
                 f"The {name} class is removed from pandas. Accessing it from "
-                "the top-level namespace will also be removed in the next "
-                "version",
+                "the top-level namespace will also be removed in the next version",
                 FutureWarning,
                 stacklevel=2,
             )

pandas/_config/config.py

@@ -165,8 +165,7 @@ def _reset_option(pat, silent=False):
         raise ValueError(
             "You must specify at least 4 characters when "
             "resetting multiple keys, use the special keyword "
-            '"all" to reset all the options to their default '
-            "value"
+            '"all" to reset all the options to their default value'
         )
 
     for k in keys:

pandas/_libs/index.pyx

@@ -85,7 +85,6 @@ cdef class IndexEngine:
         """
         cdef:
             object loc
-            void* data_ptr
 
         loc = self.get_loc(key)
         if isinstance(loc, slice) or util.is_array(loc):
@@ -101,7 +100,6 @@ cdef class IndexEngine:
         """
         cdef:
             object loc
-            void* data_ptr
 
         loc = self.get_loc(key)
         value = convert_scalar(arr, value)

pandas/core/indexes/datetimelike.py

@@ -156,13 +156,11 @@ def equals(self, other) -> bool:
     def __contains__(self, key):
         try:
             res = self.get_loc(key)
-            return (
-                is_scalar(res)
-                or isinstance(res, slice)
-                or (is_list_like(res) and len(res))
-            )
         except (KeyError, TypeError, ValueError):
             return False
+        return bool(
+            is_scalar(res) or isinstance(res, slice) or (is_list_like(res) and len(res))
+        )
 
     # Try to run function on index first, and then on elements of index
     # Especially important for group-by functionality
@@ -875,11 +873,7 @@ def _is_convertible_to_index_for_join(cls, other: Index) -> bool:
 
     def _wrap_joined_index(self, joined, other):
         name = get_op_result_name(self, other)
-        if (
-            isinstance(other, type(self))
-            and self.freq == other.freq
-            and self._can_fast_union(other)
-        ):
+        if self._can_fast_union(other):
             joined = self._shallow_copy(joined)
             joined.name = name
             return joined

pandas/core/ops/__init__.py

@@ -664,8 +664,7 @@ def to_series(right):
 
         elif right.ndim > 2:
             raise ValueError(
-                "Unable to coerce to Series/DataFrame, dim "
-                f"must be <= 2: {right.shape}"
+                f"Unable to coerce to Series/DataFrame, dim must be <= 2: {right.shape}"
             )
 
     elif is_list_like(right) and not isinstance(right, (ABCSeries, ABCDataFrame)):

pandas/core/reshape/melt.py

@@ -52,8 +52,7 @@ def melt(
             if not missing.empty:
                 raise KeyError(
                     "The following 'id_vars' are not present "
-                    "in the DataFrame: {missing}"
-                    "".format(missing=list(missing))
+                    f"in the DataFrame: {list(missing)}"
                 )
     else:
         id_vars = []
@@ -74,8 +73,7 @@ def melt(
             if not missing.empty:
                 raise KeyError(
                     "The following 'value_vars' are not present in "
-                    "the DataFrame: {missing}"
-                    "".format(missing=list(missing))
+                    f"the DataFrame: {list(missing)}"
                 )
         frame = frame.loc[:, id_vars + value_vars]
     else:

pandas/core/reshape/merge.py

@@ -600,13 +600,11 @@ def __init__(
 
         if not is_bool(left_index):
             raise ValueError(
-                "left_index parameter must be of type bool, not "
-                "{left_index}".format(left_index=type(left_index))
+                f"left_index parameter must be of type bool, not {type(left_index)}"
             )
         if not is_bool(right_index):
             raise ValueError(
-                "right_index parameter must be of type bool, not "
-                "{right_index}".format(right_index=type(right_index))
+                f"right_index parameter must be of type bool, not {type(right_index)}"
             )
 
         # warn user when merging between different levels
@@ -1092,8 +1090,7 @@ def _maybe_coerce_merge_keys(self):
                         warnings.warn(
                             "You are merging on int and float "
                             "columns where the float values "
-                            "are not equal to their int "
-                            "representation",
+                            "are not equal to their int representation",
                             UserWarning,
                         )
                     continue
@@ -1103,8 +1100,7 @@ def _maybe_coerce_merge_keys(self):
                         warnings.warn(
                             "You are merging on int and float "
                             "columns where the float values "
-                            "are not equal to their int "
-                            "representation",
+                            "are not equal to their int representation",
                             UserWarning,
                         )
                     continue
@@ -1251,20 +1247,17 @@ def _validate(self, validate: str):
                 )
             elif not left_unique:
                 raise MergeError(
-                    "Merge keys are not unique in left dataset; "
-                    "not a one-to-one merge"
+                    "Merge keys are not unique in left dataset; not a one-to-one merge"
                 )
             elif not right_unique:
                 raise MergeError(
-                    "Merge keys are not unique in right dataset; "
-                    "not a one-to-one merge"
+                    "Merge keys are not unique in right dataset; not a one-to-one merge"
                 )
 
         elif validate in ["one_to_many", "1:m"]:
             if not left_unique:
                 raise MergeError(
-                    "Merge keys are not unique in left dataset; "
-                    "not a one-to-many merge"
+                    "Merge keys are not unique in left dataset; not a one-to-many merge"
                 )
 
         elif validate in ["many_to_one", "m:1"]:
@@ -1833,8 +1826,7 @@ def _left_join_on_index(left_ax: Index, right_ax: Index, join_keys, sort: bool =
             raise AssertionError(
                 "If more than one join key is given then "
                 "'right_ax' must be a MultiIndex and the "
-                "number of join keys must be the number of "
-                "levels in right_ax"
+                "number of join keys must be the number of levels in right_ax"
             )
 
         left_indexer, right_indexer = _get_multiindex_indexer(
@@ -2004,8 +1996,7 @@ def _validate_operand(obj: FrameOrSeries) -> "DataFrame":
             return obj.to_frame()
     else:
         raise TypeError(
-            "Can only merge Series or DataFrame objects, "
-            "a {obj} was passed".format(obj=type(obj))
+            f"Can only merge Series or DataFrame objects, a {type(obj)} was passed"
         )
 
 
@@ -2021,10 +2012,7 @@ def _items_overlap_with_suffix(left: Index, lsuffix, right: Index, rsuffix):
         return left, right
 
     if not lsuffix and not rsuffix:
-        raise ValueError(
-            "columns overlap but no suffix specified: "
-            "{rename}".format(rename=to_rename)
-        )
+        raise ValueError(f"columns overlap but no suffix specified: {to_rename}")
 
     def renamer(x, suffix):
         """
@@ -2043,7 +2031,7 @@ def renamer(x, suffix):
         x : renamed column name
         """
         if x in to_rename and suffix is not None:
-            return "{x}{suffix}".format(x=x, suffix=suffix)
+            return f"{x}{suffix}"
         return x
 
     lrenamer = partial(renamer, suffix=lsuffix)

pandas/core/reshape/tile.py

@@ -363,8 +363,7 @@ def _bins_to_cuts(
 
     if duplicates not in ["raise", "drop"]:
         raise ValueError(
-            "invalid value for 'duplicates' parameter, "
-            "valid options are: raise, drop"
+            "invalid value for 'duplicates' parameter, valid options are: raise, drop"
         )
 
     if isinstance(bins, IntervalIndex):

pandas/core/tools/datetimes.py

@@ -231,9 +231,7 @@ def _return_parsed_timezone_results(result, timezones, tz, name):
     """
     if tz is not None:
         raise ValueError(
-            "Cannot pass a tz argument when "
-            "parsing strings with timezone "
-            "information."
+            "Cannot pass a tz argument when parsing strings with timezone information."
         )
     tz_results = np.array(
         [Timestamp(res).tz_localize(zone) for res, zone in zip(result, timezones)]
@@ -817,8 +815,7 @@ def f(value):
         required = ",".join(req)
         raise ValueError(
             "to assemble mappings requires at least that "
-            f"[year, month, day] be specified: [{required}] "
-            "is missing"
+            f"[year, month, day] be specified: [{required}] is missing"
         )
 
     # keys we don't recognize

pandas/core/window/common.py

@@ -98,8 +98,7 @@ def _flex_binary_moment(arg1, arg2, f, pairwise=False):
         and isinstance(arg2, (np.ndarray, ABCSeries, ABCDataFrame))
     ):
         raise TypeError(
-            "arguments to moment function must be of type "
-            "np.ndarray/Series/DataFrame"
+            "arguments to moment function must be of type np.ndarray/Series/DataFrame"
         )
 
     if isinstance(arg1, (np.ndarray, ABCSeries)) and isinstance(

pandas/core/window/rolling.py

@@ -1820,8 +1820,7 @@ def _on(self) -> Index:
         else:
             raise ValueError(
                 f"invalid on specified as {self.on}, "
-                "must be a column (of DataFrame), an Index "
-                "or None"
+                "must be a column (of DataFrame), an Index or None"
             )
 
     def validate(self):
@@ -1838,9 +1837,8 @@ def validate(self):
             # we don't allow center
             if self.center:
                 raise NotImplementedError(
-                    "center is not implemented "
-                    "for datetimelike and offset "
-                    "based windows"
+                    "center is not implemented for "
+                    "datetimelike and offset based windows"
                 )
 
             # this will raise ValueError on non-fixed freqs
@@ -1886,8 +1884,7 @@ def _validate_freq(self):
         except (TypeError, ValueError):
             raise ValueError(
                 f"passed window {self.window} is not "
-                "compatible with a datetimelike "
-                "index"
+                "compatible with a datetimelike index"
             )
 
     _agg_see_also_doc = dedent(

pandas/io/excel/_util.py

@@ -136,8 +136,7 @@ def _maybe_convert_usecols(usecols):
     if is_integer(usecols):
         raise ValueError(
             "Passing an integer for `usecols` is no longer supported.  "
-            "Please pass in a list of int from 0 to `usecols` "
-            "inclusive instead."
+            "Please pass in a list of int from 0 to `usecols` inclusive instead."
         )
 
     if isinstance(usecols, str):

pandas/io/formats/format.py

@@ -737,12 +737,8 @@ def _to_str_columns(self) -> List[List[str]]:
                 self.header = cast(List[str], self.header)
                 if len(self.header) != len(self.columns):
                     raise ValueError(
-                        (
-                            "Writing {ncols} cols but got {nalias} "
-                            "aliases".format(
-                                ncols=len(self.columns), nalias=len(self.header)
-                            )
-                        )
+                        f"Writing {len(self.columns)} cols "
+                        f"but got {len(self.header)} aliases"
                     )
                 str_columns = [[label] for label in self.header]
             else:

pandas/io/formats/html.py

@@ -216,8 +216,8 @@ def _write_table(self, indent: int = 0) -> None:
                 self.classes = self.classes.split()
             if not isinstance(self.classes, (list, tuple)):
                 raise TypeError(
-                    "classes must be a string, list, or tuple, "
-                    "not {typ}".format(typ=type(self.classes))
+                    "classes must be a string, list, "
+                    f"or tuple, not {type(self.classes)}"
                 )
             _classes.extend(self.classes)
 

pandas/io/formats/latex.py

@@ -114,8 +114,7 @@ def pad_empties(x):
                 column_format = index_format + column_format
         elif not isinstance(self.column_format, str):  # pragma: no cover
             raise AssertionError(
-                "column_format must be str or unicode, "
-                "not {typ}".format(typ=type(column_format))
+                f"column_format must be str or unicode, not {type(column_format)}"
             )
         else:
             column_format = self.column_format

pandas/io/sas/sas.pyx

@@ -267,8 +267,9 @@ cdef class Parser:
             elif column_types[j] == b's':
                 self.column_types[j] = column_type_string
             else:
-                raise ValueError("unknown column type: "
-                                 f"{self.parser.columns[j].ctype}")
+                raise ValueError(
+                    f"unknown column type: {self.parser.columns[j].ctype}"
+                )
 
         # compression
         if parser.compression == const.rle_compression:

pandas/io/sas/sas7bdat.py

@@ -459,8 +459,7 @@ def _process_columnsize_subheader(self, offset, length):
         if self.col_count_p1 + self.col_count_p2 != self.column_count:
             print(
                 f"Warning: column count mismatch ({self.col_count_p1} + "
-                f"{self.col_count_p2} != "
-                f"{self.column_count})\n"
+                f"{self.col_count_p2} != {self.column_count})\n"
             )
 
     # Unknown purpose
@@ -672,8 +671,7 @@ def _read_next_page(self):
             self.close()
             msg = (
                 "failed to read complete page from file (read "
-                f"{len(self._cached_page):d} of "
-                f"{self._page_length:d} bytes)"
+                f"{len(self._cached_page):d} of {self._page_length:d} bytes)"
             )
             raise ValueError(msg)
 

pandas/io/sas/sasreader.py

@@ -49,8 +49,7 @@ def read_sas(
     if format is None:
         buffer_error_msg = (
             "If this is a buffer object rather "
-            "than a string name, you must specify "
-            "a format string"
+            "than a string name, you must specify a format string"
         )
         filepath_or_buffer = stringify_path(filepath_or_buffer)
         if not isinstance(filepath_or_buffer, str):